Predictive Models for University Dropout at UNIRIO

• Henrique Soares Rodrigues UNIRIO
• Laura O. Moraes UNIRIO
• Reinaldo Viana Alvares UNIRIO

DOI: https://doi.org/10.5753/cbie_estendido.2025.11700

Resumo

Dropout rates in higher education are a challenge faced by Higher Education Institutions (HEIs), with personal, academic, and social impacts. This research aims to analyze dropout rates in exact sciences courses at UNIRIO using data science and predictive artificial intelligence techniques. Three studies were conducted: a systematic mapping of the literature on AI algorithms applied to dropout rates, a prediction of dropout rates in the Information Systems course with Decision Tree using only academic data, and a broader analysis with Gradient Boosting, including data from the Federal Revenue Service and Annual Report of Social Information (RAIS), to verify the influence of formal employment and entrepreneurship up to the fourth semester. The results indicate that academic performance is the main factor related to dropout rates, while employment and entrepreneurship did not show significant influence.

Referências

Baker, R., Isotani, S., and Carvalho, A. (2011). Mineraçao de dados educacionais: Oportunidades para o brasil. Revista Brasileira de informática na educação, 19(02):03.

Bardagi, M. and Hutz, C. S. (2005). Evasão universitária e serviços de apoio ao estudante: uma breve revisão da literatura brasileira. Psicologia Revista, 14(2):279–301.

Brasil (2012). Art.14 da portaria mec nº 18/2012. Diário Oficial da República Federativa do Brasil.

Brasil (2018). Lei nº 13.709, de 14 de agosto de 2018. Diário Oficial da República Federativa do Brasil.

Brasil (2023). Censo da educação superior. [link]. Acessed in 10/30/2024.

Caton, S. and Haas, C. (2024). Fairness in machine learning: A survey. ACM Comput. Surv., 56(7).

de la Cruz-Campos, J.-C., Victoria-Maldonado, J.-J., Martínez-Domingo, J.-A., and Campos-Soto, M.-N. (2023). Causes of academic dropout in higher education in andalusia and proposals for its prevention at university: A systematic review. In Frontiers in Education, volume 8, page 1130952. Frontiers Media SA.

Freire, J., Landim, F., Moraes, L., Delgado, C., and Pedreira, C. (2024). Modelo para previsão precoce de abandono de uma disciplina de introdução à programação. In Anais do XXXII Workshop sobre Educação em Computação, pages 635–645, Porto Alegre, RS, Brasil. SBC.

Friedman, J. (2000). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29.

Kehm, B. M., Larsen, M. R., and Sommersel, H. B. (2019). Student dropout from universities in Europe: A review of empirical literature. Hungarian Educational Research Journal, 9(2):147 – 164. Place: Budapest, Hungary Publisher: Akadémiai Kiadó.

Kitchenham, B., Madeyski, L., and Budgen, D. (2023). Segress: Software engineering guidelines for reporting secondary studies. IEEE Transactions on Software Engineering, 49(3):1273–1298.

Moraes, L. O. and Pedreira, C. E. (2020). Designing an intelligent tutoring system across multiple classes. In CSEDM@EDM.

Osman, A. F. (2019). Radiation oncology in the era of big data and machine learning for precision medicine. Artificial Intelligence-Applications in Medicine and Biology. IntechOpen, pages 41–70.

Prestes, E. M. d. T. and Fialho, M. G. D. (2018). Evasão na educação superior e gestão institucional: o caso da universidade federal da paraíba. Ensaio: Avaliação e Políticas Públicas em Educação, 26:869–889.

Provost, F. and Fawcett, T. (2016). Data Science for Business: What You Need to Know about Data Mining and Data-Analytic Thinking.

Realinho, V., Machado, J., Baptista, L., and Martins, M. V. (2022). Predicting student dropout and academic success. Data, 7(11).

Rodrigues, H., Moraes, L., and Alvares, R. (2025). Predictive models for university dropout at unirio. Master’s thesis.

Rodrigues, H., Moraes, L., Santiago, E., Campos, J., Júnior, E. G., Wanderley, G., Garcia, A., Mello, C., Alvares, R., and Santos, R. (2024a). Predicting student dropout on the information systems undergraduate program of unirio using decision trees. In Anais do XXXII Workshop sobre Educação em Computação, pages 588–598, Porto Alegre, RS, Brasil. SBC.

Rodrigues, H., Santiago, E., Wanderley, G., Moraes, L., Eduardo Mello, C., Alvares, R., and Santos, R. (2024b). Artificial intelligence algorithms to predict college students’ dropout: A systematic mapping study. In Proceedings of the 16th International Conference on Agents and Artificial Intelligence - Volume 3: ICAART, pages 344–351. INSTICC, SciTePress.

Saccaro, A., França, M. T. A., and Jacinto, P. d. A. (2019). Fatores associados à evasão no ensino superior brasileiro: um estudo de análise de sobrevivência para os cursos das áreas de ciência, matemática e computação e de engenharia, produção e construção em instituições públicas e privadas. Estudos Econômicos (São Paulo), 49:337–373.

Samuel, A. L. (1967). Some studies in machine learning using the game of checkers. ii—recent progress. IBM Journal of research and development, 11(6):601–617.

Seidl, M., Scholz, M., Huemer, C., and Kappel, G. (2015). The Use Case Diagram, pages 23–47. Springer International Publishing, Cham.

Silva, J. and Roman, N. (2021). Predicting dropout in higher education: a systematic review. In Anais do XXXII Simpósio Brasileiro de Informática na Educação, pages 1107–1117, Porto Alegre, RS, Brasil. SBC.

Tete, M. F., Sousa, M. d. M., de Santana, T. S., and Silva, S. F. (2022). Predictive models for higher education dropout: A systematic literature review. Education Policy Analysis Archives, 30:(149).

Tinto, V. (1975). Drop-outs from higher education: A theoretical synthesis of recent research. Review of Educational Research, 45:89–125.

Ugoni, A. and Walker, B. F. (1995). The chi square test: an introduction. COMSIG review, 4(3):61.

Von Foerster, H. (2003). Ethics and second-order cybernetics. Understanding understanding: Essays on cybernetics and cognition, pages 287–304.

White, S. A. (2004). Introduction to bpmn. Ibm Cooperation, 2(0):0.